Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.1986. Min Act: -0.1700

Data Index: 227191 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.1986. Min Act: -0.1700

Data Index: 7990 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.2298. Min Act: -0.1700

Data Index: 15524 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.1673. Min Act: -0.1700

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0736. Min Act: -0.1700

Data Index: 1155264 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0736. Min Act: -0.1700

Data Index: 1010799 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0736. Min Act: -0.1700

Data Index: 260992 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0736. Min Act: -0.1700

Data Index: 382587 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0423. Min Act: -0.1700

Data Index: 206354 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0111. Min Act: -0.1700

Data Index: 845721 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 5.2298. Min Range: -5.2298

Max Act: 4.9798. Min Act: -0.1700

Data Index: 1053035 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 5.2298. Min Range: -5.2298

Max Act: 4.9798. Min Act: -0.1700

Data Index: 618895 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0423. Min Act: -0.1700

Data Index: 953147 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0111. Min Act: -0.1700

Data Index: 1103664 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0423. Min Act: -0.1700

Data Index: 223089 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 5.2298. Min Range: -5.2298

Max Act: 4.9486. Min Act: -0.1700

Data Index: 794902 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 5.2298. Min Range: -5.2298

Max Act: 5.0423. Min Act: -0.1700

Data Index: 656477 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 5.2298. Min Range: -5.2298

Max Act: 4.9173. Min Act: -0.1700

Data Index: 149421 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 5.2298. Min Range: -5.2298

Max Act: 4.8548. Min Act: -0.1700

Data Index: 153536 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 5.2298. Min Range: -5.2298

Max Act: 4.8861. Min Act: -0.1700

Data Index: 293912 (C4 (Web Text))

Max Activating Token Index: 256